Workshop
Fri Jul 28 12:00 PM -- 08:00 PM (PDT) @ Meeting Room 323 None
Structured Probabilistic Inference and Generative Modeling
The workshop focuses on theory, methodology, and application of structured probabilistic inference and generative modeling, both of which are important topics in machine learning.Specifically, probabilistic inference addresses the problem of amortization,sampling, and integration of complex quantities from graphical models, while generative modeling captures the underlying probability distributions of a dataset. Apart from applications in computer vision, natural language processing, and speech recognition, probabilistic inference and generative modeling approaches have also been widely used in natural science domains, including physics, chemistry, molecular biology, and medicine. Despite the promising results, probabilistic methods face challenges when applied to highly structured data, which are ubiquitous in real-world settings, limiting the applications of such methods. This workshop aims to bring experts from diverse backgrounds and related domains together to discuss the applications and challenges of probabilistic methods. The workshop will emphasize challenges in encoding domain knowledge when learning representations, performing inference and generations. By bringing together experts from academia and industry, the workshop will provide a platform for researchers to share their latest results and ideas, fostering collaboration and discussion in the field of probabilistic methods.
| Opening Remark | |
| Invited Talk by Karen Ullrich (Invited Talk) | |
| Invited Talk by Tommi Jaakkola (Invited Talk) | |
| Coffee Break (Break) | |
| Invited Talk by Durk Kingma (Invited Talk) | |
| Collapsed Inference for Bayesian Deep Learning (Contributed Talk) | |
| Provable benefits of score matching (Contributed Talk) | |
| Poster Session 1 (Poster Session) | |
| Panel Discussion | |
| Invited Talk by Ruqi Zhang (Invited Talk) | |
| Invited Talk by Stefano Ermon (Invited Talk) | |
| BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery (Contributed Talk) | |
| Generative Marginalization Models (Contributed Talk) | |
| Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network (Contributed Talk) | |
| Closing Remark | |
| Poster Session 2 (Poster Session) | |
| Your Diffusion Model is Secretly a Zero-Shot Classifier (Poster) | |
| Test-time Adaptation with Diffusion Models (Poster) | |
| Beyond Confidence: Reliable Models Should Also Consider Atypicality (Poster) | |
| Implications of kernel mismatch for OOD data (Poster) | |
| Scaling Graphically Structured Diffusion Models (Poster) | |
| Diffusion map particle systems for generative modeling (Poster) | |
| C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder (Poster) | |
| An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets (Poster) | |
| Nonparametric posterior normalizing flows (Poster) | |
| Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models (Poster) | |
| Diffusion Probabilistic Models Generalize when They Fail to Memorize (Poster) | |
| Solving Inverse Physics Problems with Score Matching (Poster) | |
| Attention as Implicit Structural Inference (Poster) | |
| Prediction under Latent Subgroup Shifts with High-dimensional Observations (Poster) | |
| Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network (Oral) | |
| Diffusion Based Causal Representation Learning (Poster) | |
| Provable benefits of score matching (Oral) | |
| An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (Poster) | |
| Nested Diffusion Processes for Anytime Image Generation (Poster) | |
| Training Diffusion Models with Reinforcement Learning (Poster) | |
| Generating Turn-Based Player Behavior via Experience from Demonstrations (Poster) | |
| Automatic Rao-Blackwellization for Sequential Monte Carlo with Belief Propagation (Poster) | |
| Collaborative Score Distillation for Consistent Visual Synthesis (Poster) | |
| Exploring Exchangeable Dataset Amortization for Bayesian Posterior Inference (Poster) | |
| Function Space Bayesian Pseudocoreset for Bayesian Neural Networks (Poster) | |
| Beyond Intuition, a Framework for Applying GPs to Real-World Data (Poster) | |
| Identifying Under-Reported Events in Networks with Spatial Latent Variable Models (Poster) | |
| Generative Marginalization Models (Oral) | |
| Early Exiting for Accelerated Inference in Diffusion Models (Poster) | |
| MissDiff: Training Diffusion Models on Tabular Data with Missing Values (Poster) | |
| Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data (Poster) | |
| CM-GAN: Stabilizing GAN Training with Consistency Models (Poster) | |
| Flow Matching for Scalable Simulation-Based Inference (Poster) | |
| Learning Linear Causal Representations from Interventions under General Nonlinear Mixing (Poster) | |
| Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection (Poster) | |
| Causal Discovery with Language Models as Imperfect Experts (Poster) | |
| HiGen: Hierarchical Graph Generative Networks (Poster) | |
| Fast and Functional structured data generator (Poster) | |
| Structured Neural Networks for Density Estimation (Poster) | |
| Diffusion Generative Inverse Design (Poster) | |
| Tree Variational Autoencoders (Poster) | |
| Morse Neural Networks for Uncertainty Quantification (Poster) | |
| STable Permutation-based Framework for Table Generation in Sequence-to-Sequence Models (Poster) | |
| Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policies (Poster) | |
| Neuro-Causal Factor Analysis (Poster) | |
| Autoregressive Diffusion Models with non-Uniform Generation Order (Poster) | |
| Variational Point Encoding Deformation for Dental Modeling (Poster) | |
| BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery (Oral) | |
| On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization (Poster) | |
| Uncovering Latent Structure Using Random Partition Models (Poster) | |
| Improving Training of Likelihood-based Generative Models with Gaussian Homotopy (Poster) | |
| Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Markov Chains (Poster) | |
| Lexinvariant Language Models (Poster) | |
| BatchGFN: Generative Flow Networks for Batch Active Learning (Poster) | |
| Anomaly Detection in Networks via Score-Based Generative Models (Poster) | |
| PRODIGY: Enabling In-context Learning Over Graphs (Poster) | |
| Dimensionality Reduction as Probabilistic Inference (Poster) | |
| DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models (Poster) | |
| Diffusion Probabilistic Models for Structured Node Classification (Poster) | |
| Large Dimensional Change Point Detection with FWER Control as Automatic Stopping (Poster) | |
| Score-based Enhanced Sampling for Protein Molecular Dynamics (Poster) | |
| Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes (Poster) | |
| Reinforcement Learning-Driven Linker Design via Fast Attention-based Point Cloud Alignment (Poster) | |
| AbODE: Ab initio antibody design using conjoined ODEs (Poster) | |
| Inferring Hierarchical Structure in Multi-Room Maze Environments (Poster) | |
| Parallel Sampling of Diffusion Models (Poster) | |
| PITS: Variational Pitch Inference Without Fundamental Frequency for End-to-End Pitch-Controllable TTS (Poster) | |
| Regularized Data Programming with Automated Bayesian Prior Selection (Poster) | |
| On the Identifiability of Markov Switching Models (Poster) | |
| Optimizing protein fitness using Bi-level Gibbs sampling with Graph-based Smoothing (Poster) | |
| Robust and Scalable Bayesian Online Changepoint Detection (Poster) | |
| GSURE-Based Diffusion Model Training with Corrupted Data (Poster) | |
| Hierarchical Graph Generation with $K^{2}$-trees (Poster) | |
| Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences (Poster) | |
| Thompson Sampling for Improved Exploration in GFlowNets (Poster) | |
| GFlowNets for Causal Discovery: an Overview (Poster) | |
| Concept Algebra for Score-based Conditional Model (Poster) | |
| Diffusion Models with Grouped Latents for Interpretable Latent Space (Poster) | |
| Multilevel Control Functional (Poster) | |
| HINT: Hierarchical Coherent Networks For Constrained Probabilistic Forecasting (Poster) | |
| Balanced Training of Energy-Based Models with Adaptive Flow Sampling (Poster) | |
| Practical and Asymptotically Exact Conditional Sampling in Diffusion Models (Poster) | |
| Generative semi-supervised learning with a neural seq2seq noisy channel (Poster) | |
| Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation (Poster) | |
| Conditional Graph Generation with Graph Principal Flow Network (Poster) | |
| Deep Generative Clustering with Multimodal Variational Autoencoders (Poster) | |
| Graph Neural Network Powered Bayesian Optimization for Large Molecular Spaces (Poster) | |
| The Pairwise Prony Algorithm: Efficient Inference of Stochastic Block Models with Prescribed Subgraph Densities (Poster) | |
| Plug-and-Play Controllable Graph Generation with Diffusion Models (Poster) | |
| The Local Inconsistency Resolution Algorithm (Poster) | |
| Towards Modular Learning of Deep Causal Generative Models (Poster) | |
| Pretrained Language Models to Solve Graph Tasks in Natural Language (Poster) | |
| Non-Normal Diffusion Models (Poster) | |
| A Generative Model for Text Control in Minecraft (Poster) | |
| Visual Chain-of-Thought Diffusion Models (Poster) | |
| Collapsed Inference for Bayesian Deep Learning (Oral) | |